MCP serverdev.workers.manhliemcn4euwlu.llmrt-companion/mcp-agent-security
Security scanner for AI agents and MCP servers: injection, jailbreak, tool abuse.
Overview
Score?
UNRATED 0.000
of what a free look can see, on 7 looks
Looks
7
last 6 hr ago
Tools
5
More info
URL
llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-agent-security
streamable-http
Says it is
llm-red-team-scanner 1.0
protocol 2025-06-18
In the record since
14 days ago
Among servers32,729 with a card
0median 0.547 · this server 0.000 · highest on record 0.8351
Toolsfrom sha256:2db5822c97…a69b01
| Tool | Schema |
|---|---|
| get_pricing PRO pricing & payment info: 44 probes / 20 attack classes / 0-100 score / CI gate / per-class remediation, 0.15 XNO (ERC-20 or Lightning) or card. |
input · no output |
| get_purchase_flow Machine-readable autonomous purchase procedure: how an agent pays (0.15 XNO, or USDC on Base via x402) and receives the PRO download with no human in the loop (callback push + poll |
input · no output |
| get_scan_result Poll a scan by job id (returned by run_free_scan) until status=done. |
input · no output |
| run_free_scan Free LLM agent security review in ~35s. Two parts: (1) 8 live adversarial probes (jailbreak / prompt injection / system-prompt extraction / tool abuse) against your agent spec, and |
input · no output |
| validate Judge one delivery against the task's own acceptance rule and return {verdict: accepted|rejected, reason}. Called by the brick.blue hub when this seat is drawn as validator. Judges |
input · no output |
Verify it yourself
npx teppi-check https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-agent-securitycurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M6JHX4D5B3CQ0711HC3KK0WK